Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1165 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 10.8642. Min Range: -10.8642

Max Act: 10.8642. Min Act: -0.0000

Data Index: 1382924 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 10.8642. Min Range: -10.8642

Max Act: 10.1249. Min Act: -0.0000

Data Index: 1794352 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 10.8642. Min Range: -10.8642

Max Act: 10.5489. Min Act: -0.0000

Data Index: 1004294 (The Pile)

Max Activating Token Index: 218

Text #3

Max Range: 10.8642. Min Range: -10.8642

Max Act: 10.1699. Min Act: -0.0000

Data Index: 1680812 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 10.8642. Min Range: -10.8642

Max Act: 10.1717. Min Act: -0.0000

Data Index: 444229 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.7446. Min Act: -0.0000

Data Index: 1174904 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 10.8642. Min Range: -10.8642

Max Act: 10.2186. Min Act: -0.0000

Data Index: 326493 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 10.8642. Min Range: -10.8642

Max Act: 10.2029. Min Act: -0.0000

Data Index: 809627 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 10.8642. Min Range: -10.8642

Max Act: 10.1623. Min Act: -0.0000

Data Index: 1776682 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.8211. Min Act: -0.0000

Data Index: 671257 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.9700. Min Act: -0.0000

Data Index: 675066 (The Pile)

Max Activating Token Index: 169

Text #11

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.5816. Min Act: -0.0000

Data Index: 1842704 (The Pile)

Max Activating Token Index: 5

Text #12

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.8365. Min Act: -0.0000

Data Index: 505270 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.6649. Min Act: -0.0000

Data Index: 1116563 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.6649. Min Act: -0.0000

Data Index: 660310 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.5302. Min Act: -0.0000

Data Index: 1945413 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.6935. Min Act: -0.0000

Data Index: 1201121 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.7987. Min Act: -0.0000

Data Index: 518562 (The Pile)

Max Activating Token Index: 5

Text #18

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.6044. Min Act: -0.0000

Data Index: 1829060 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 10.8642. Min Range: -10.8642

Max Act: 9.2147. Min Act: -0.0000

Data Index: 837617 (The Pile)

Max Activating Token Index: 579